Image processing in floriculture using a robotic mobile platform

Colombia has a privileged geographical location which makes it a cornerstone and equidistant point to all regional markets. The country has a great ecological diversity and it’s one of the largest suppliers of flowers for US. Colombian flower companies have made innovations in the marketing process, using methods to reach all conditions for final consumers. Nowadays, Robotic has performed a significant role in agriculture thanks to its the level of accuracy. Examples of this are all developments in computer vision, allowing greater control over production processes such as quality inspection, selection and classification of a product according to market requirements, ensuring high quality standards in production for exporting, optimizing performance times at the production level, among others.

Computer vision is based on image processing, method used for identifying environment objects and making decisions about their behavior. The main tasks of the vision system are detecting, segmenting and recognizing patterns, integrating systems of digital image capture, input-output devices and computer networks.

The image processing in real time using artificial vision systems applied in floriculture is mainly focused on the use of techniques and methods to obtain, process and analyze the information provided by the images of different types of flowers to export. In this case, fulfilling the goal of quality inspection system checks the compliance of a flower with certain characteristics in their appearance, such as size, uniformity of color, brightness, etc.

A new research article develops a monitoring system for floriculture industries. The system was implemented in a robotic platform. This device has the ability to be programmed in different programming languages. The robot takes the necessary environment information from its camera. The algorithm of the monitoring system was developed with the image processing toolbox on Matlab. The implemented algorithm acquires images through its camera, it performs a pre-processing of the image, noise filter, enhancing of the color and adjusting the dimension in order to increase processing speed. Then, the image is segmented by color and with the binarized version of the image using morphological operations (erosion and dilation), extract relevant features such as centroid, perimeter and area. The data obtained from the image processing helps the robot with the automatic identification of objectives, orientation and move towards them. Also, the results generate a diagnostic quality of each object scanned.

Access the full study at Cornell University